Search

Stroke is an injury that abruptly affects brain tissues. This disease is caused by a change in the blood supply to a particular region of the brain, and it results in the loss or reduction of its related functions. Cerebral vascular accidents affect 16 million people worldwide every year, and 6 million of these people die. However, another important problem related to strokes, besides mortality, is that many survivors have chronic consequences that are complex and heterogeneous. In this paper, a new approach to identify and classify stroke from a structural co-occurrence matrix (SCM) in skull CT images. To state the efficiency of the technique considered, a comparison with other important and well-known state-of-art feature extractors was performed. In addition, SCM was evaluated with two high-pass filters (Laplacian and Sobel) and two low-pass filters (Median and Gaussian). Regarding classifiers, Bayesian classifier, Optimum-Path Forest (OPF) and Support Vector Machines were used. The proposed approach using its optimal configuration and the OPF classifier with Euclidean distance had the highest average accuracy (99.40%), and the extraction time low, similar to other ones widely used and well known.